Information Theory

Towards a Unified Information-Theoretic Framework for Generalization NeurIPS 2021 What About the Precedent: An Information-Theoretic Analysis of Common Law NAACL 2021 Which Mutual-Information Representation Learning Objectives are Sufficient for Control? NeurIPS 2021 A mathematical theory of cooperative communication NeurIPS 2020 An approximate KLD based experimental design for models with intractable likelihoods AISTATS 2020 An Information-Theoretic Quantification of Discrimination with Exempt Features AAAI 2020 Applications of Common Entropy for Causal Inference NeurIPS 2020 Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Networks JMLR 2020 CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information ICML 2020 Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds NeurIPS 2020 Context Aware Local Differential Privacy ICML 2020 Decentralized Multi-player Multi-armed Bandits with No Collision Information AISTATS 2020 Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks NeurIPS 2020 Estimating Mutual Information Between Dense Word Embeddings ACL 2020 Fast Unbalanced Optimal Transport on a Tree NeurIPS 2020 Formal Limitations on the Measurement of Mutual Information AISTATS 2020 Imputation estimators for unnormalized models with missing data AISTATS 2020 Infomax Neural Joint Source-Channel Coding via Adversarial Bit Flip AAAI 2020 Information theoretic limits of learning a sparse rule NeurIPS 2020 Information-Theoretic Probing with Minimum Description Length EMNLP 2020 Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing ICML 2020 It’s Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information ACL 2020 Less is Better: A cognitively inspired unsupervised model for language segmentation COLING 2020 Limits on Testing Structural Changes in Ising Models NeurIPS 2020 Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms NeurIPS 2020